11 October 2024 : Clinical Research
Predicting Neonatal Hypoglycemia Using AI Neural Networks in Infants from Mothers with Gestational Diabetes Mellitus
Zhimin Zhang1ABCDEFG, Ying Feng1ABCDEF, Yu Zhang2ABC, Xia Li1ABC, Yanfei Li3BCF, Lulu Sun1BC, Xianying Li1D, Hui Du1AEFG, Jingxiao Zhang1AEFG*DOI: 10.12659/MSM.944513
Med Sci Monit 2024; 30:e944513
Figure 2 The neural network computational models for estimating neonate blood concentrations(A) Artificial neural network (ANN) model to predict the lowest neonate blood concentration/hypoglycemia in the first 24 h of life. The proposed model included 16 input variables, 8 neurons in the hidden layer, and 1 output variable. (B) Recurrent neural network (RNN) model to predict neonate blood concentrations in the first 24 h of life. The proposed model included 16 input variables, 50 units in the hidden layer, 8 neurons in the dense layer, and 1 output variable.